Okan Köpüklü's starred repositories
active-speakers-context
Code for the Active Speakers in Context Paper (CVPR2020)
Driver-Anomaly-Detection
PyTorch Implementation of "Driver Anomaly Detection: A Dataset and Contrastive Learning Approach", codes and pretrained models.
SupContrast
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
ctc-segmentation
Segment an audio file and obtain utterance alignments. (Python package)
Driver-Intention-Prediction
A framework predicts driver's maneuver behaviors
blitz-bayesian-deep-learning
A simple and extensible library to create Bayesian Neural Network layers on PyTorch.
CVPR2020-HAttMatting
Attention-Guided Hierarchical Structure Aggregation for Image Matting(CVPR2020)
pytorch-CAM
Class Activation Mapping written in PyTorch.
info8010-deep-learning
Lectures for INFO8010 Deep Learning, ULiège
tracking-with-Extended-Kalman-Filter
Object (e.g Pedestrian, vehicles) tracking by Extended Kalman Filter (EKF), with fused data from both lidar and radar sensors.
STAGE_action_detection
Code of the STAGE module for video action detection
mahalanobis_3d_multi_object_tracking
[NeurIPS Workshop 2019] Official code of the paper "Probabilistic 3D Multi-Object Tracking for Autonomous Driving." First Place of the First NuScenes Tracking Challenge in the AI Driving Olympics Workshop of NeurIPS.
pretrained-models.pytorch
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
oxford-poster
LaTeX beamer poster template themed for the University of Oxford
lemniscate.pytorch
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Kalman-and-Bayesian-Filters-in-Python
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
SSL-2D-Pose
Code for the paper "Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments"
ig65m-pytorch
PyTorch 3D video classification models pre-trained on 65 million Instagram videos
stmodeling
Code for the paper "Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos"
pydensecrf
Python wrapper to Philipp Krähenbühl's dense (fully connected) CRFs with gaussian edge potentials.